Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3590 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.7379. Min Act: -0.0000

Data Index: 917298 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.8908. Min Act: -0.0000

Data Index: 1270838 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.3881. Min Act: -0.0000

Data Index: 766872 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.1677. Min Act: -0.0000

Data Index: 785982 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1930661 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.1966. Min Act: -0.0000

Data Index: 1426953 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.2484. Min Act: -0.0000

Data Index: 14748 (The Pile)

Max Activating Token Index: 325

Text #7

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.1458. Min Act: -0.0000

Data Index: 776483 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1303074 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.1636. Min Act: -0.0000

Data Index: 1489073 (The Pile)

Max Activating Token Index: 85

Text #10

Max Range: 1.8908. Min Range: -1.8908

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1821755 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1215143 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.0816. Min Act: -0.0000

Data Index: 713292 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 1.8908. Min Range: -1.8908

Max Act: 0.9436. Min Act: -0.0000

Data Index: 187577 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1739695 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.0485. Min Act: -0.0000

Data Index: 943013 (The Pile)

Max Activating Token Index: 787

Text #16

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.0428. Min Act: -0.0000

Data Index: 617992 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.0354. Min Act: -0.0000

Data Index: 1263775 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.0276. Min Act: -0.0000

Data Index: 396879 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.0626. Min Act: -0.0000

Data Index: 341830 (The Pile)

Max Activating Token Index: 45